upstream-archive byte-perfect snapshot of Helsinki-NLP/opus-mt-eo-sh (ADR-039 Phase D)

.gitattributes

@@ -1,35 +1,10 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,98 @@
+---
+language: 
+- eo
+- sh
+
+tags:
+- translation
+
+license: apache-2.0
+---
+
+### epo-hbs
+
+* source group: Esperanto 
+* target group: Serbo-Croatian 
+*  OPUS readme: [epo-hbs](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/epo-hbs/README.md)
+
+*  model: transformer-align
+* source language(s): epo
+* target language(s): bos_Latn hrv srp_Cyrl srp_Latn
+* model: transformer-align
+* pre-processing: normalization + SentencePiece (spm4k,spm4k)
+* a sentence initial language token is required in the form of `>>id<<` (id = valid target language ID)
+* download original weights: [opus-2020-06-16.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/epo-hbs/opus-2020-06-16.zip)
+* test set translations: [opus-2020-06-16.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/epo-hbs/opus-2020-06-16.test.txt)
+* test set scores: [opus-2020-06-16.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/epo-hbs/opus-2020-06-16.eval.txt)
+
+## Benchmarks
+
+| testset               | BLEU  | chr-F |
+|-----------------------|-------|-------|
+| Tatoeba-test.epo.hbs 	| 13.6 	| 0.351 |
+
+
+### System Info: 
+- hf_name: epo-hbs
+
+- source_languages: epo
+
+- target_languages: hbs
+
+- opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/epo-hbs/README.md
+
+- original_repo: Tatoeba-Challenge
+
+- tags: ['translation']
+
+- languages: ['eo', 'sh']
+
+- src_constituents: {'epo'}
+
+- tgt_constituents: {'hrv', 'srp_Cyrl', 'bos_Latn', 'srp_Latn'}
+
+- src_multilingual: False
+
+- tgt_multilingual: False
+
+- prepro:  normalization + SentencePiece (spm4k,spm4k)
+
+- url_model: https://object.pouta.csc.fi/Tatoeba-MT-models/epo-hbs/opus-2020-06-16.zip
+
+- url_test_set: https://object.pouta.csc.fi/Tatoeba-MT-models/epo-hbs/opus-2020-06-16.test.txt
+
+- src_alpha3: epo
+
+- tgt_alpha3: hbs
+
+- short_pair: eo-sh
+
+- chrF2_score: 0.35100000000000003
+
+- bleu: 13.6
+
+- brevity_penalty: 0.888
+
+- ref_len: 17999.0
+
+- src_name: Esperanto
+
+- tgt_name: Serbo-Croatian
+
+- train_date: 2020-06-16
+
+- src_alpha2: eo
+
+- tgt_alpha2: sh
+
+- prefer_old: False
+
+- long_pair: epo-hbs
+
+- helsinki_git_sha: 480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535
+
+- transformers_git_sha: 2207e5d8cb224e954a7cba69fa4ac2309e9ff30b
+
+- port_machine: brutasse
+
+- port_time: 2020-08-21-14:41

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-eo-sh",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      7346
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 7346,
+  "decoder_vocab_size": 7347,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 7347,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 7346,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.22.0.dev0",
+  "use_cache": true,
+  "vocab_size": 7347
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      7346
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 7346,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 7346,
+  "renormalize_logits": true,
+  "transformers_version": "4.32.0.dev0"
+}

metadata.json

@@ -0,0 +1 @@
+{"hf_name":"epo-hbs","source_languages":"epo","target_languages":"hbs","opus_readme_url":"https:\/\/github.com\/Helsinki-NLP\/Tatoeba-Challenge\/tree\/master\/models\/epo-hbs\/README.md","original_repo":"Tatoeba-Challenge","tags":["translation"],"languages":["eo","sh"],"src_constituents":["epo"],"tgt_constituents":["hrv","srp_Cyrl","bos_Latn","srp_Latn"],"src_multilingual":false,"tgt_multilingual":false,"prepro":" normalization + SentencePiece (spm4k,spm4k)","url_model":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/epo-hbs\/opus-2020-06-16.zip","url_test_set":"https:\/\/object.pouta.csc.fi\/Tatoeba-MT-models\/epo-hbs\/opus-2020-06-16.test.txt","src_alpha3":"epo","tgt_alpha3":"hbs","short_pair":"eo-sh","chrF2_score":0.351,"bleu":13.6,"brevity_penalty":0.888,"ref_len":17999.0,"src_name":"Esperanto","tgt_name":"Serbo-Croatian","train_date":"2020-06-16","src_alpha2":"eo","tgt_alpha2":"sh","prefer_old":false,"long_pair":"epo-hbs","helsinki_git_sha":"480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535","transformers_git_sha":"2207e5d8cb224e954a7cba69fa4ac2309e9ff30b","port_machine":"brutasse","port_time":"2020-08-21-14:41"}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ecb40a05b8223d37a81250a657412bd6bb48541564002c2d9b1e993d38ec292
+size 193781001

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e15f290ca900277c47e7fe22328d8ad78c35a1b7391ca4eb6f5887fa4d6824d
+size 302685

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6ef01db1cd98ad2daaffd9f358381276d9346394fbf9f72576a8bc1297d6c5
+size 303038

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f11f53fc292b4dd43fb6f07612f8ec05aafdc543554c2025bd9105de419cbc
+size 194043976

tokenizer_config.json

@@ -0,0 +1 @@
+{"target_lang": "hbs", "source_lang": "epo"}